# Beyond the Aggregation Dilemma: Prior-Retaining Decoupled Learning for Multimodal Graphs

arXiv: https://arxiv.org/abs/2605.24684 · HTML: https://mlsanity.com/paper/2605.24684/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 23 May 2026.

## Builds on (most cited first, 19 of 19)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Representation Learning on Graphs with Jumping Knowledge Networks](https://mlsanity.com/paper/1806.03536/) (2018)
- [Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View](https://mlsanity.com/paper/1909.03211/) (2019)
- [Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs](https://mlsanity.com/paper/2307.03393/) (2023)
- [Gradient Starvation: A Learning Proclivity in Neural Networks](https://mlsanity.com/paper/2011.09468/) (2020)
- [Balanced Multimodal Learning via On-the-fly Gradient Modulation](https://mlsanity.com/paper/2203.15332/) (2022)
- [Revisiting Graph Neural Networks: All We Have is Low-Pass Filters](https://mlsanity.com/paper/1905.09550/) (2019)
- [Improving Multi-Modal Learning with Uni-Modal Teachers](https://mlsanity.com/paper/2106.11059/) (2021)
- [Learning on Multimodal Graphs: A Survey](https://mlsanity.com/paper/2402.05322/) (2024)
- [When Graph meets Multimodal: Benchmarking and Meditating on Multimodal Attributed Graphs Learning](https://mlsanity.com/paper/2410.09132/) (2024)
- [DGP: A Dual-Granularity Prompting Framework for Fraud Detection with Graph-Enhanced LLMs](https://mlsanity.com/paper/2507.21653/) (2025)
- [Unleash LLMs Potential for Sequential Recommendation by Coordinating Dual Dynamic Index Mechanism](https://mlsanity.com/paper/2409.09253/) (2024)
- [Deep Semantic Graph Learning via LLM based Node Enhancement](https://mlsanity.com/paper/2502.07982/) (2025)

## Abstract (arXiv)

Multimodal Attributed Graph Learning (MAGL) integrates intrinsic node attributes with structural topology via graph aggregation. However, as pretrained encoders evolve into Large Foundation Models (LFMs), the landscape of MAGL fundamentally shifts: under high-confidence LFM priors, mandatory aggregation introduces topological noise that overwhelms discriminative signals, triggering a counter-intuitive performance inversion where sophisticated MAGL architectures underperform simple topology-agnostic MLPs. Through systematic empirical and theoretical analysis, we identify that this inversion stems from a fundamental aggregation dilemma characterized by two concurrent pathologies: (1) Representational Pathology (SNR Degradation) - mandatory aggregation dilutes robust intrinsic features with topological noise, causing the noise penalty to outweigh its collaborative benefit; and (2) Optimization Pathology (Gradient Starvation) - topological aggregation attenuates gradient flow, while a shared task loss causes dominant modalities to prematurely suppress weaker ones. To resolve this dilemma, we propose SUPRA (Shared-Unique Prior-Retaining Architecture), a decoupled dual-pathway paradigm. SUPRA processes modality-specific features through topology-agnostic MLPs while capturing structural synergy via a lightweight shared GNN, with auxiliary deep supervision counteracting gradient starvation. Extensive evaluations demonstrate that SUPRA achieves state-of-the-art performance while requiring 3.5x lower peak GPU memory and up to 4.4x faster training time than Multimodal Graph Transformers.